Model comparison
Gemini 2.0 Flash-Lite vs GPT-5 Nano
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 33.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 6 categories and GPT-5 Nano in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.0 Flash-Lite leads 51.7 to 39.1.
- The biggest single-benchmark swing is GPQA (HELM): 50% for Gemini 2.0 Flash-Lite and 67.9% for GPT-5 Nano.
Side by side
| Gemini 2.0 Flash-Lite | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.8 | 33.5 |
| Released | 2025-02-05 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 32 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 37.9 (#185), GPT-5 Nano: 33.6 (#254)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1322 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| LiveBench Coding | 47.1% | — |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, GPT-5 Nano: 25.8 (#106)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
Reasoning Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 22.0 (#210), GPT-5 Nano: 16.3 (#306)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1328 |
| DTBench | 52.5% | 62.7% |
| ForecastBench | 57.1 | 59.1 |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| LiveBench Reasoning | 50.1% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.38 |
| LiveBench | 54.3% | — |
Math Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 34.1 (#196), GPT-5 Nano: 29.4 (#241)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| Omni-MATH | 37.4% | 54.6% |
| LMArena Math | 1309 | 1317 |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Too close to call
Gemini 2.0 Flash-Lite: 35.0 (#189), GPT-5 Nano: 35.9 (#178)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| MMLU-Pro | 72% | 77.8% |
| GPQA (HELM) | 50% | 67.9% |
| LMArena Expert | 1305 | 1321 |
| GPQA Diamond | — | 69.4% |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 10.5% |
Multimodal Too close to call
Gemini 2.0 Flash-Lite: 31.2 (#109), GPT-5 Nano: 31.3 (#108)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1100 | 1159 |
| VPCT | — | 37.2% |
Multilingual Too close to call
Gemini 2.0 Flash-Lite: 46.0 (#161), GPT-5 Nano: 45.3 (#172)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1323 | 1313 |
| LMArena Chinese | 1339 | 1356 |
| LMArena German | 1306 | 1327 |
| LMArena Japanese | 1301 | 1226 |
| LMArena Korean | 1325 | 1269 |
| LMArena Russian | 1328 | 1296 |
| LMArena Spanish | 1313 | 1360 |
| LMArena French | 1347 | — |
Instruction Following GPT-5 Nano leads
Gemini 2.0 Flash-Lite: 70.4 (#163), GPT-5 Nano: 75.0 (#79)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| IFEval | 82.4% | 93.2% |
| LMArena Instruction Following | 1305 | 1306 |
| LiveBench Instruction Following | 78.3% | — |
Long Context Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 40.1 (#160), GPT-5 Nano: 31.3 (#281)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1320 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 51.7 (#177), GPT-5 Nano: 39.1 (#249)
| Benchmark | Gemini 2.0 Flash-Lite | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1330 | 1320 |
| LMArena Creative Writing | 1319 | 1249 |
| WildBench | 79% | 80.6% |
| LMArena Multi-Turn | 1307 | 1311 |
| EQ-Bench Creative Writing | — | 705 |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than GPT-5 Nano?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.8 to 33.5 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or GPT-5 Nano better for coding?
Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.9 versus 33.6 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and GPT-5 Nano share?
24 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and GPT-5 Nano has 49.